Program at Glance

Time zone: Dubai Time (GMT +4)

Zoom link for the keynotes: https://zu-ac-ae.zoom.us/j/97702866406

Tuesday, November 26th, 2024
08:00-17:00	Registartion
9:00-10:15	Technical Session 1	Chair: Kristián Košťál and Ben Koska
		Can Large Language Model detect plagiarism in source code? William Brach, Kristián Košťál and Michal Ries Towards Multi-Modal Mastery: A 4.5B Parameter Truly Multi-Modal Small Language Model Ben Koska and Mojmír Horváth VLM-Auto: VLM-based Autonomous Driving Assistant with Human-like Behavior and Understanding for Complex Road Scenes Ziang Guo, Zakhar Yagudin, Artem Lykov, Mikhail Konenkov and Dzmitry Tsetserukou Text-based Personality Prediction Using Large Language Models Maria Molchanova and Daria Olshevskaya YOLO based Object detection Enhancement based on quadratic convolution Abdesselam Ferdi, Amir Nakib
10:15 -10:45	Coffee Break
10:45-11:45	Technical Session 2	Chair: Chanyeol Choi and Nenad Petrovic
		Understanding Open Source Large Language Models: An Exploratory Study Sulayman Sowe, Yongli Mou, Alexander Neumann, Du Cheng, Lingxiao Kong and Stefan Decker The Design and Implementation of APLOS: An Automated PoLicy DOcument Summarisation System Sulayman Sowe, Tobias Kiel, Alexander Neumann, Yongli Mou, Vassilios Peristeras and Stefan Decker Adopting RAG for LLM-Aided Future Vehicle Design Vahid Zolfaghari, Nenad Petrovic, Fengjunjie Pan, Krzysztof Lebioda and Alois Knoll Can Separators Improve Chain-of-Thought Prompting? Yoonjeong Park, Hyunjin Kim, Chanyeol Choi, Junseong Kim and Jy-Yong Sohn
11:45-12:00	Opening Notes
12:00-1:00	Keynote 1: Davor Svetinovic Beyond Blockchain Censorship Zoom Link: https://zu-ac-ae.zoom.us/j/97702866406
13:00 -14:00	Lunch Break
14:00-15:30	Technical Session 3	Chair: Vitor Gaboardi dos Santos and Belbachir Faiza
		Diverse Utterances Generation with GPT to Improve Task-Oriented Chatbots and APIs Integration Vitor Gaboardi dos Santos, Boualem Benatallah, Auday Berro and Silvana MacMahon Detecting Health Misinformation on Social Networking Sites Using Large Language Models and Deep Learning-based Natural Language Processing Amenah Alshahrani, Hafiz Farooq and Jamil Hussain Enhancing Named Entity Recognition in Arabic: Leveraging Transformer-Based Models and Open Data Sources Faiza Belbachir and Assia Soukane Keep it Local: Comparing Domain-Specific LLMs in Native and Machine Translated Text using Parallel Corpora on Political Conflict Javier Osorio, Sultan Alsarra, Amber Converse, Afraa Alshammari, Dagmar Heintze, Naif Alatrush, Latifur Khan, Patrick T. Brandt, Vito D'Orazio, Niamat Zawad and Mahrusa Billah From Scarcity to Sufficiency: Machine Translation Techniques for Low-Resource LLMs Enhancement Hao Yang, Min Zhang and Jiaxin Guo Brain tumor extraction method using KNN algorithm by the K parameter variation Samir Bara, Sara Sennouni, Ayoub Jibouni
15:30-16:00	Coffee Break
16:00-17:30	Technical Session 4	Chair: Amina El Ganadi and Shadi Alzubi
		Empirical Evaluation of Social Bias in Text Classification Systems Lynda Djennane, Zsolt T. Kardkovacs, Boualem Benatallah, Yacine Gaci, Walid Gaaloul and Zoubeyr Farah Using LLMs for Evaluating QA Systems: Exploration and Assessment Hadel Alhawasi and Abdou Youssef A Comparative Evaluation of Artificial Intelligence-Based Models in Retinal Image Synthesis Farida Mohsen, Ali Aldhubri, Md.Rafiul Biswas and Zubair Shah The Impact of Generative AI on Islamic Studies: Case Analysis of “Digital Muhammad ibn Ismāʿīl al-Bukhārī” Amina El Ganadi, Sania Aftar, Luca Gagliardelli, Sonia Bergamaschi and Federico Ruozzi LLM-Driven Testing for Autonomous Driving Scenarios Nenad Petrovic, Krzysztof Lebioda, Vahid Zolfaghari, André Schamschurko, Sven Kirchner, Nils Purschke, Fengjunjie Pan and Alois Knoll Investigating Social Bias in GPT-4: A Study on Race Representation Tarun Mahesh
19:00-20:30	Welcome Reception

Wednesday, November 27th, 2024
08:00-17:00	Registartion
9:00-10:15	Technical Session 5: LLMs4MI Workshop Meeting Link: https://meet.google.com/paz-crtc-kdp	Chair: Sulayman Sowe and Yongli Mou
		Screening Automation for Systematic Reviews: A 5-Tier Prompting Approach Meeting Cochrane’s Sensitivity Requirement Elias Sandner, Bing Hu, Alice Simiceanu, Luca Fontana, Igor Jakovljevic, Andre Henriques, Andreas Wagner and Christian Gütl From Rehab to Recap: Generating Discharge Reports for Rehabilitation Clinics with LLMs Sabine Kugler, Dario Antweiler and Benny Stein Prompting Large Language Models for Supporting the Differential Diagnosis of Anemia Elisa Castagnari, Lillian Muyama and Adrien Coulet RadLink: Linking Clinical Entities from Radiology Reports Yongli Mou, Hanbin Chen, Gwendolyn Lode, Daniel Truhn, Sulayman Sowe and Stefan Decker Large Language Models for Literature Reviews - An Exemplary Comparison of LLM-based Approaches with Manual Methods Julia Gehrmann, Lars Quakulinski and Oya Beyan
10:15 -10:45	Coffee Break
10:45-12:00	Technical Session 6 Meeting Link: https://meet.google.com/paz-crtc-kdp	Chair: Dzmitry Tsetserukou and Yaser Jararweh
		Effects of Language- and Culture-Specific Prompting on ChatGPT Mustafa Tuna, Kristina Schaaff and Tim Schlippe Robots Can Feel: LLM-based Framework for Robot Ethical Reasoning Artem Lykov, Miguel Altamirano Cabrera, Koffivi Fidèle Gbagbe and Dzmitry Tsetserukou LLM-BRAIn: AI-driven Fast Generation of Robot Behaviour Tree based on Large Language Model Artem Lykov and Dzmitry Tsetserukou MissionGPT: Mission Planner for Mobile Robot based on Robotics Transformer Model Vladimir Berman, Artem Bazhenov and Dzmitry Tsetserukou Utilizing LLMs for Enhancing Search Engine Optimization Strategies in Digital Marketing Tariq Samarah, Tawfiq Alrawashdeh, Ala Mughaid, Shadi Alzubi
12:00-1:00	Keynote 2: Samson Lasaulce LLMs, optimization, and game theory Zoom Link: https://zu-ac-ae.zoom.us/j/97702866406
13:00 -14:00	Lunch Break
14:00-15:00	Keynote 3: Berick Cook Autonomous Intelligent Reinforcement Interpreted Symbolism (AIRIS): Beyond Reinforcement Learning Zoom Link: https://zu-ac-ae.zoom.us/j/97702866406
15:00-15:30	Coffee Break
15:30-17:00	Technical Session 8: GENAIDOC Workshop Meeting Link: https://meet.google.com/paz-crtc-kdp	Chair: Rafika Boutalbi and Rim Hantach
		Invited Talk: A systematic approach to fusioning LLM with Machine learning tasks through the Linear Representation hypothesis. Kave Salamatian, The University of Savoie Mont Blanc LLM-centric pipeline for information extraction from invoices Faiza Loukil, Sarah Cadereau, Hervé Verjus, Mattéo Galfre, Kavé Salamatian, David Telisson, Quentin Kembellec and Olivier Le Van Fake News Detection Using Large Language Models and Sentiment Analysis Wissam Bouaraki, Asma Saibi, Yasmine Guerbai and Abdenour Hadid Efficacy of Large Language Models in Systematic Reviews Aaditya Shah, Shridhar Mehendale and Siddha Kanthi Short Paper: Capturing Bias Diversity in LLMs Purva Prasad Gosavi, Vaishnavi Murlidhar Kulkarni and Alan Smeaton Towards a scalable AI-driven framework for data-independent Cyber Threat Intelligence Information Extraction Olga Sorokoletova, Emanuele Antonioni and Giordano Colò
17:00-18:00	Technical Session 7: PromptEng Workshop 1 Meeting Link: https://meet.google.com/paz-crtc-kdp	Chair: Shadi AlZubi and Matthew Renze
		Prompting and Fine-Tuning of Small LLMs for Length-Controllable Telephone Call Summarization David Thulke, Yingbo Gao, Rricha Jalota, Christian Dugast and Hermann Ney NiftyLLaMA: An open information extraction system integrated with sentiment analysis for Nifty-50 companies using LLaMa-2 Kiran Kumar Kotha and Varsha Yadav Prompt Engineering as Code (PEaC): an approach for building modular, reusable, and portable prompts Gaetano Perrone and Simon Pietro Romano Self-Reflection in Large Language Model Agents: Effects on Problem-Solving Performance Matthew Renze and Erhan Guven The Benefits of a Concise Chain of Thought on Problem-Solving in Large Language Models Matthew Renze and Erhan Guven
20:00-22:00	Gala Dinner and Awards Ceremony

Thursday, November 28th, 2024
08:00-17:00	Registartion
9:00-10:15	Technical Session 9: Online Meeting Link: https://sharjah-ac-ae.zoom.us/j/91595832631	Chair: Christos Troussas and Kashif Bilal
		Modeling Llama-2 into Joint Source-Channel Coding for Semantic Communication Shiva Raj Pokhrel and Anwar Walid Feature-Centric Mobile Applications Clustering with Generative AI Sana Saeed, Kashif Bilal, Junaid Shuja, Abdallah Namoun and Isa Ali Pantami Evaluating ChatGPT-driven Automated Test Generation for Personalized Programming Education Christos Troussas, Christos Papakostas, Akrivi Krouska, Phivos Mylonas and Cleo Sgouropoulou ChatGPT-based Recommendations for Personalized Content Creation and Instructional Design with a Tailored Prompt Generator Akrivi Krouska, Christos Troussas, Ioannis Voyiatzis, Phivos Mylonas and Cleo Sgouropoulou Fake News Detection with Retrieval Augmented Generative Artificial Intelligence Mohammad Vatani Nezafat and Saeed Samet Detecting Academic Misconduct: A BERT-Based Approach to Identifying ChatGPT-Generated Content Abdalla Shawabkeh, Abdulla Hassooni, Faten F. Kharbat and Sahel Alouneh
10:15 -10:45	Coffee Break
10:45-12:00	Technical Session 10: Foundation Models and Special Tracks Meeting Link: https://sharjah-ac-ae.zoom.us/j/91595832631	Chair: Rajesh Pasupuleti and Garima Agrawal
		Popular LLM Models in Enterprise Applications Rajesh Pasupuleti, Ravi Vadapalli, Christopher Mader, Norris Timothy Mindful-RAG: A Study of Points of Failure in Retrieval Augmented Generation Garima Agrawal, Tharindu Kumarage, Zeyad Alghamdi and Huan Liu Can bidirectional encoder become the ultimate winner for downstream applications of foundation models? Lewen Yang, Xuanyu Zhou, Juao Fan, Xinyi Xie and Shengxin Zhu Understanding Foundation Models: Are We Back in 1924? Alan Smeaton Predicting Groundwater Levels at Colorado State of USA Using ARIMA And ANN Models Hifsa Ghafoor, Rahila Umer, Fatima Ali, Jan Muhammad, Zahid Rauf and Pamir Khan From Pixels to Paragraphs: Extraction of Text from Medical Reports using LLMs, Systematic Literature Review Muhammad Sadiq, Ramsha Tariq, Anayat Ullah and Jeneen Panezai
12:00-1:00	Keynote 3: Albert Zomaya Generative AI at the Edge: Enhancing Local Data Processing for Real-Time Applications Zoom Link: https://zu-ac-ae.zoom.us/j/97702866406
13:00 -14:00	Lunch Break
14:00-15:30	Technical Session 11: Online Meeting Link: https://sharjah-ac-ae.zoom.us/j/91595832631	Chair: Tristan Kenneweg and Lee Kuan
		Adaptive Composite Accuracy Scoring for Domain-specific LLM Evaluation Jocelyn Shuang Ru Teh, Eng Keong Koay, Shin Wei Lim, Kuan Heng Lee, Mee Sim Lai, Meng Siong Lee and Yuan Kuok Nee Methodologies for Selecting Optimal Hardware for Locally Deployed LLMs Using a Performance, Accuracy and Cost (PAC) Approach Kuan Heng Lee, Mee Sim Lai, Shin Wei Lim, Jocelyn Shuang Ru Teh, Syafie Nizam, Yuan Kuok Nee, Eng Keong Koay and Meng Siong Lee Teaching Large Language Models to Understand Jeju Island with Domain-Adaptive Pretraining Jae Young Suh, Eunchan Lee, Yohan Jeong, Donggil Park and Sung-Min Ahn Introducing LLMScript: A Turing Complete Prompt Based Scripting Language for LLMs with No External Coding Required Shahin Mowzoon and Mishkin Faustini RAGVAL: Automatic Dataset Creation and Evaluation for RAG Systems Tristan Kenneweg, Philip Kenneweg and Barbara Hammer When to Inject? Investigating Different Metrics for Conditional Context Injection in LLMs Tristan Kenneweg, Philip Kenneweg and Barbara Hammer
15:30-16:00	Coffee Break
16:00-17:30	Technical Session 12: GenAISE and LLMCS Workshops Meeting Link: https://sharjah-ac-ae.zoom.us/j/91595832631	Chair: Muna Al-Hawawreh and Kristina Schaaff
		Comparative Analysis of Loop-Free Function Evaluation Using ChatGPT and Copilot with C Bounded Model Checking Faten Slama and Daniel Lemire A Systematic Study on the Potentials and Limitations of LLM-assisted Software Development Chiara Michelutti, Jens Eckert, Milko Monecke, Julian Klein and Sabine Glesner Evaluating Large Language Models for Code Generation: Assessing Accuracy, Quality, and Performance Mohammed Shehab, Mohammad Wardat, Safwan Omari and Yaser Jararweh Large Multimodal Agents for Accurate Phishing Detection with Enhanced Token Optimization and Cost Reduction Fouad Trad and Ali Chehab The Impact of Large Language Models on IT Security in the Corporate Environment Sebastian Scholz, Alexander Lawall and Kristina Schaaff An Early Investigation into the Utility of Multimodal Large Language Models in Medical Imaging Sulaiman Khan, Fathima Farha, Manahil Zulfiqar, Md. Rafiul Biswas and Zubair Shah Empowering Cyber Defense: Unveiling AI-Powered Expert Systems and Software Engineering Lo'Ai Tawalbeh, John Franklin, Christian Ramirez, Jonathan Garcia, Abdelrahman Tawalbeh and Fadi Muheidat
17:30-18:00	On Site Closing Ceremony

Friday, November 29th, 2024
9:15-10:45	Technical Session 13: PromptEng Workshop and Online Meeting Link: https://mbzuai-ac-ae.zoom.us/j/98715272764	Chair: Stanislav Selitskiy and Shadi Alzubi
		Ethical and Legal Considerations of Large Language Models: A Systematic Review of the Literature. Shahad Alkamli, Maha Al-Yahya and Khulood Alyahya Exploring the Potential of LLMs and Attributed Prompt Engineering for Efficient Text Generation and Labeling Wedyan Alsakran and Reham Alabduljabbar Provoking Unstable and Evasive ChatGPT Behaviour with Anti-chain-of-thought: Japanese Rock Song Lyrics Case, A Year Later Stanislav Selitskiy and Chihiro Inoue Language Models at the Edge: A Survey on Techniques, Challenges, and Applications Siem Hadish, Velibor Bojkovic, Moayad Aloqaily and Mohsen Guizani Prompt Engineering for Enhancing Clinical Pharmacy Decision Support through LLMs Majd Abu Alshieh, Muder Almiani, Walid Al-Qerem, Abdel Qader Al Bawab, Shadi Alzubi Prompt Engineering in Business Analytics for Next-Gen Digital Banking Services Fatima Qiyam, Yousef Jaradat, Shadi Alzubi Evaluating Robustness of Neural Networks on Rotationally Disrupted Datasets for Semantic Segmentation Akshar Patel
10:45 -11:00	Break
11:00-12:30	Technical Session 14: Online Meeting Link: https://mbzuai-ac-ae.zoom.us/j/98715272764	Chair: Rand Kouatlyl and Yaser Jararweh
		A Metric for Evaluating Stable Diffusion Models using Attention Map Haruno Fusa, Chonho Lee, Sakuei Onishi and Hiromitsu Shiina Comparative Analysis of Reasoning Capabilities in Foundation Models J. de Curtò and I. de Zarzà Generative AI Agents, Build a Multilingual ChatGPT-based Customer Service Chatbot Rand Kouatly, Nien-Ying Chou, Suleiman Alabdallah Self-healing automation testing with Selenium and ChatGPT API integration to improve the efficiency of the maintenance Rand Kouatly, Yunjin Kim Bridging the Gap: A comparative Analysis of ICS and IT Datasets for IDS Evaluation Sai Sree Koneru and Jake Cho Automatic classification of text messages by confidentiality level based on ensemble of artificial neural networks Alexey Sulavko, Yuri Varkentin, Irina Panfilova, Alexander Samotuga